Decision tree classification of land cover from remotely sensed data

Decision tree classification algorithms have significant potential for land cover mapping problems and have not been tested in detail by the remote sensing community relative to more conventional pattern recognition techniques such as maximum likelihood classification. In this paper, we present several types of decision tree classification algorithms arid evaluate them on three different remote sensing data sets. The decision tree classification algorithms tested include an univariate decision tree, a multivariate decision tree, and a hybrid decision tree capable of including several different types of classification algorithms within a single decision tree structure. Classification accuracies produced by each of these decision tree algorithms are compared with both maximum likelihood and linear discriminant function classifiers. Results from this analysis show that the decision tree algorithms consistently outperform the maximum likelihood and linear discriminant function classifiers in regard to classf — cation accuracy. In particular, the hybrid tree consistently produced the highest classification accuracies for the data sets tested. More generally, the results from this work show that decision trees have several advantages for remote sensing applications by virtue of their relatively simple, explicit, and intuitive classification structure. Further, decision tree algorithms are strictly nonparametric and, therefore, make no assumptions regarding the distribution of input data, and are flexible and robust with respect to nonlinear and noisy relations among input features and class labels.

Heavy Metals in Soil and Crops of an Intensively Farmed Area: A Case Study in Yucheng City, Shandong Province, China

lThe study was supported by the Knowledge Innovation Foundation of the institute of Geographical Sciences and Natural Resource, Chinese Academy of Sciences (Grant No. 200906002) and Key Directional Project of Knowledge Innovation of Chinese Academy of Sciences (Grant No. KSCX2-YW-N-46-01). The authors would like to thank to Luke Driskell for his kind help and hard work on English language polishing of the article.

Quantitative structure-property relationship research to the analysis of photoionization sensitivity of organic compounds in gas chromatography

The A(m) index and molecular connectivity index were used for studying the photoionization sensitivity of some organic compounds in gas chromatography. The analysis of structure-property relationship between the photoionization sensitivity of the compounds and the A(m) indices or molecular connectivity indices has been carried out. The genetic algorighm was used to build the correlation model in this field. The results demonstrate that the property of compounds can be described by both A(m) indices and molecular connectivity indices, and the mathematical model obtained by the genetic algorithm was better than that by multivariate regression analysis.

Simultaneous spectrophotometric determination of zinc, cadmium and mercury with hybrid linear analysis

A new method for simultaneous spectrophotometric determination of Zn, Cd and Hg using 2-(5-Br-2-pyridylazo)-5-diethylaminophenol as the color developing reagent was proposed. The absorption spectra of these three complexes have similar features with severe overlap in visible spectral range. For resolving these spectra, hybrid linear analysis was used, and the pure spectrum of each component was obtained from the calibration mixtures by least squares method. The effects of reaction condition, selection of wavelengths, determination of pure spectrum and additivity of absorbances etc. on the determination were discussed. The proposed method offers the advantages of simple, rapid, and accuracy. It has been successfully applied to the simultaneous determination of Zn, Cd and Hg in synthetic sample. A comparison was also made with the partial least squares method.

Simultaneous spectrophotometric determination of trace iron (III) and aluminum (III) with hybrid linear analysis

Hybrid linear analysis (HLA) was applied to resolution of overlapping spectra of Fe3+-salicylfluorone and Al3+-salicylfluorone complexes and simultaneous spectrophotometric determination of Fe3+ and Al3+. The absorbance matrix of 7 standard mixtures at 41 measuring points ranged from the wavelength of 550 nm to 630 nm was used for calibration. To avoid the effect of interaction between the two components on the determination, the column vector of K matrix obtained from the standard mixtures with least squares was used as the pure spectrum of component. The recoveries of the two elements for the analysis of the synthetic samples were 93.3% similar to 107.5% in the range of the concentration ratio of Fe3+:Al3+ = 10:1 to 1:8. Comparing with the partial least squares (PIS) model, the HLA method was simple, accuracy and precise.

Quantitative structure-property relationships for colour reagents and their colour reactions with cerium using computational neural networks

Quantitative structure-activity/property relationships (QSAR/QSPR) studies have been exploited extensively in the designs of drugs and pesticides, but few such studies have been applied to the design of colour reagents. In this work, the topological indices A(x1)-A(x3) suggested in this laboratory were applied to multivariate analysis in structure-property studies. The topological indices of 43 phosphone bisazo derivatives of chromotropic acid were calculated. The structure-property relationships between colour reagents and their colour reactions with cerium were studied using A(x1-Ax3) indices with satisfactory results. The purpose of this work was to establish whether QSAR can be used to predict the contrasts of colour reactions and in the longer term to be a helpful tool in colour reagent design.

Quantitative structure-property relationships for colour reagents and their colour reactions with ytterbium using regression analysis and computational neural networks

In this paper, the new topological indices A(x1)-A(x3) suggested in our laboratory and molecular connectivity indices have been applied to multivariate analysis in structure-property studies. The topological indices of twenty asymmetrical phosphono bisazo derivatives of chromotropic acid have been calculated. The structure-property relationships between colour reagents and their colour reactions with ytterbium have been studied by A(x1)-A(x3) indices and molecular connectivity indices with satisfactory results. Multiple regression analysis and neural networks were employed simultaneously in this study.

Study on structure-property relationships between color reagents and sensitivity of color reactions with yttrium by topological indices

In this paper, three topological indices, Am-1, Am-2, and Am-3, multivariate analysis in structure-property studies. The topological indices of twenty asymmetrical phosphosphono bisazo derivatives of chromotropic acid have been calculated. The structure-property relationships between color reagents and molar absorptivity of color reactions with yttrium have been studied by A(m) indices and structure selective factors. Good results have been obtained by using correlation equation to predict the molar absorptivity of new color reagents.

Studies on structure-property relationship between color reagents and contrast of their color reactions with cerium by topological indices

In this paper, three topological indices A(m1), A(m2) and A(m3) have been applied to multivariate analysis in structure property relationship studies. The topological indices oi fourty-three asymmetrical phosphono bisazo derivatives of chromotropic acid have been calculated, The structure-property relationship between color reagents and contrast of color reactions with cerium has been studied by A, indices and structure selective factors, Good results have been obtained.

STUDIES ON STRUCTURE-CARCINOGENIC ACTIVITY RELATIONSHIP OF N-NITROSO COMPOUNDS

The electronic parameters of 12 N-nitroso compounds have been computated with semiempirical quantum chemical calculation, and the study on the relationships between the structures of these compounds and the carcinogenic activities have been performed by using multivariate regression analysis and neural network with satisfactory results.

STUDIES ON STRUCTURE-PROPERTY RELATIONSHIP BETWEEN COLOR REAGENTS AND SENSITIVITY OF THEIR COLOR-REACTIONS WITH YTTERBIUM BY TOPOLOGICAL INDEXES

In this paper A, topological indices and molecular connectivity inidces have been applied to multivariate analysis in structure-property studies. The topological indices of twenty asymmetrical phosphone bisazo derivatives of chromotropic acid have been calculated. The structure-property relationships between color reagents and molar absorptivity of color reactions with ytterbium have been studied by A(m) indices and molecular connectivity indices. Good results have been obtained.

STUDY ON STRUCTURE-ACTIVITY-RELATIONSHIPS OF ORGANIC-COMPOUNDS - 3 NEW TOPOLOGICAL INDEXES AND THEIR APPLICATIONS

In this paper, three new topological indices, A(x1), A(x2), and A(x3), have been developed for use in multivariate analysis in structure-property relationship (SPR) and structure-activity relationship (SAR) studies. Good results have been obtained by using them to predict the physical and chemical properties and biological activities of some organic compounds.

Cross-Ocean distribution of Rhodobacterales bacteria as primary surface colonizers in temperate coastal marine waters

Bacterial surface colonization is a universal adaptation strategy in aquatic environments. However, neither the identities of early colonizers nor the temporal changes in surface assemblages are well understood. To determine the identities of the most common bacterial primary colonizers and to assess the succession process, if any, of the bacterial assemblages during early stages of surface colonization in coastal water of the West Pacific Ocean, nonnutritive inert materials (glass, Plexiglas, and polyvinyl chloride) were employed as test surfaces and incubated in seawater off the Qingdao coast in the spring of 2005 for 24 and 72 h. Phylogenetic analysis of the 16S rRNA gene sequences amplified from the recovered surface-colonizing microbiota indicated that diverse bacteria colonized the submerged surfaces. Multivariate statistical cluster analyses indicated that the succession of early surface-colonizing bacterial assemblages followed sequential steps on all types of test surfaces. The Rhodobacterales, especially the marine Roseobacter clade members, formed the most common and dominant primary surface-colonizing bacterial group. Our current data, along with previous studies of the Atlantic coast, indicate that the Rhodobacterales bacteria are the dominant and ubiquitous primary surface colonizers in temperate coastal waters of the world and that microbial surface colonization follows a succession sequence. A conceptual model is proposed based on these findings, which may have important implications for understanding the structure, dynamics, and function of marine biofilms and for developing strategies to harness or control surface-associated microbial communities.

Diversity and spatial distribution of sediment ammonia-oxidizing crenarchaeota in response to estuarine and environmental gradients in the Changjiang Estuary and East China Sea

Ammonia-oxidizing archaea (AOA) have recently been found to be potentially important in nitrogen cycling in a variety of environments, such as terrestrial soils, wastewater treatment reactors, marine waters and sediments, and especially in estuaries, where high input of anthropogenic nitrogen is often experienced. The sedimentary AOA diversity, community structure and spatial distribution in the Changjiang Estuary and the adjacent East China Sea were studied. Multivariate statistical analysis indicated that the archaeal amoA genotype communities could be clustered according to sampling transects, and the station located in an estuarine mixing zone harboured a distinct AOA community. The distribution of AOA communities correlated significantly with the gradients of surface-water salinity and sediment sorting coefficient. The spatial distribution of putative soil-related AOA in certain sampling stations indicated a strong impact of the Changjiang freshwater discharge on the marine benthic microbial ecosystem. Besides freshwater, nutrients, organic matter and suspended particles, the Changjiang Diluted Water might also contribute to the transport of terrestrial archaea into the seawater and sediments along its flow path.